RumorLens: A System for Analyzing the Impact of Rumors and Corrections in Social Media

Some rumors spread quickly and widely through social media. Journalists write about them, both to help the public understand whether they are true, and to help the public understand how widely misinformation and corrections have spread, and how they did. We describe RumorLens, a suite of interactive tools that are designed to help journalists identify new rumors on Twitter and assess the audiences that rumor and correction tweets have reached. The tools make efficient use of human labor to assess whether a rumor’s content is interesting enough to warrant further exploration, to label tweets as spreading, correcting, or unrelated to the rumor, and to analyze the rumor visually. Behind the scenes, automated learning and computation amplifies the effectiveness of that labor, making it feasible to engage journalists and the broader public to run a continuous rumor-monitoring service.